© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13709
    Prev
    Next
    INDEX
    Explanations

    phrases related to negation or prohibition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating caution or negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assemblies
    -0.72
     extracts
    -0.70
    naires
    -0.70
     accents
    -0.70
    itars
    -0.70
     backgrounds
    -0.68
     costumes
    -0.68
     Emails
    -0.67
     reviews
    -0.67
     ultras
    -0.67
    POSITIVE LOGITS
    brainer
    1.22
    starter
    1.01
    breaker
    0.91
     breaker
    0.88
    acea
    0.85
    kill
    0.85
     burner
    0.82
    requisite
    0.81
    statement
    0.80
    blow
    0.79
    Activations Density 0.307%

    No Known Activations